Detection and Rectification of Distorted
Fingerprints
Abstract
Elastic distortion of fingerprints is one of the major causes for false nonmatch. While this problem affects all fingerprint recognition applications, it is
especially dangerous in negative recognition applications, such as watch list and
de duplication applications. In such applications, malicious users may purposely
distort their fingerprints to evade identification. In this paper, we proposed novel
algorithms to detect and rectify skin distortion based on a single fingerprint
image. Distortion detection is viewed as a two-class classification problem, for
which the registered ridge orientation map and period map of a fingerprint are
used as the feature vector and a SVM classifier is trained to perform the
classification task. Distortion rectification (or equivalently distortion field
estimation) is viewed as a regression problem, where the input is a distorted
fingerprint and the output is the distortion field. To solve this problem, a database
(called reference database) of various distorted reference fingerprints and
corresponding distortion fields is built in the offline stage, and then in the online
stage, the nearest neighbor of the input fingerprint is found in the reference
database and the corresponding distortion field is used to transform the input
fingerprint into a normal one. Promising results have been obtained on three
databases containing many distorted fingerprints, namely FVC2004 DB1,
Tsinghua Distorted Fingerprint database, and the NIST SD27 latent fingerprint
database.
The main contributions of this paper are:
1) Compiling case studies of incidents where individuals were found to
have altered their fingerprints for circumventing AFIS,
2) Investigating the impact of fingerprint alteration on the accuracy of a
commercial fingerprint matcher,
3) Classifying the alterations into three major categories and suggesting
possible countermeasures,
4) Developing a technique to automatically detect altered fingerprints
based on analyzing orientation field and minutiae distribution, and
5) Evaluating the proposed technique and the NFIQ algorithm on a large
database of altered fingerprints provided by a law enforcement agency.
Experimental results show the feasibility of the proposed approach in detecting
altered fingerprints and highlight the need to further pursue this problem.
Existing System
In Existing System, since existing fingerprint quality assessment algorithms
are designed to examine if an image contains sufficient information (say,
minutiae) for matching, they have limited capability in determining if an image is a
natural fingerprint or an altered fingerprint. Obliterated fingerprints can evade
fingerprint quality control software, depending on the area of the damage. If the
affected finger area is small, the existing fingerprint quality assessment software
may fail to detect it as an altered fingerprint.
Proposed System
In Proposed System was evaluated at two levels: finger level and subject
level. At the finger level, we evaluate the performance of distinguishing between
natural and altered fingerprints. At the subject level, we evaluate the performance
of distinguishing between subjects with natural fingerprints and those with altered
fingerprints.
The proposed algorithm based on the features extracted from the
orientation field and minutiae satisfy the three essential requirements for
alteration detection algorithm:
1) Fast operational time,
2) High true positive rate at low false positive rate, and
3) Ease of integration into AFIS.
Modules
1. DETECTION OF ALTERED FINGERPRINTS
a. Normalization
b. Orientation field estimation
c. Orientation field approximation
d. Feature extraction
2. ANALYSIS OF MINUTIAE DISTRIBUTION
Modules Description
1. DETECTION OF ALTERED FINGERPRINTS
A. NORMALIZATION
An input fingerprint image is normalized by cropping a rectangular region
of the fingerprint, which is located at the center of the fingerprint and aligned
along the longitudinal direction of the finger, using the NIST Biometric Image
Software (NBIS). This step ensures that the features extracted in the subsequent
steps are invariant with respect to translation and rotation of finger.
B. ORIENTATION FIELD ESTIMATION
The orientation field of the fingerprint is computed using the gradientbased method. The initial orientation field is smoothed averaging filter, followed
by averaging the orientations in pixel blocks. A foreground mask is obtained by
measuring the dynamic range of gray values of the fingerprint image in local
blocks and morphological process for filling holes and removing isolated blocks is
performed.
C. ORIENTATION FIELD APPROXIMATION
The orientation field is approximated by a polynomial model to obtain.
D. FEATURE EXTRACTION
The error map is computed as the absolute difference between and used
to construct the feature vector.
2. ANALYSIS OF MINUTIAE DISTRIBUTION
In this module, a minutia in the fingerprint indicates ridge characteristics
such as ridge ending or ridge bifurcation. Almost all fingerprint recognition
systems use minutiae for matching. In addition to the abnormality observed in
orientation field, we also noted that minutiae distribution of altered fingerprints
often differs from that of natural fingerprints.
Based on the minutiae extracted from a fingerprint by the open source
minutiae extractor in NBIS, a minutiae density map is constructed by using the
Parzen window method with uniform kernel function.
SYSTEM REQUIREMENT SPECIFICATION
HARDWARE REQUIREMENTS
System
:
Pentium IV 2.4 GHz.
Hard Disk
:
80 GB.
Monitor
:
15 VGA Color.
Mouse
:
Logitech.
Ram
:
512 MB.
SOFTWARE REQUIREMENTS
Operating system
:
Windows 7 Ultimate
Front End
:
Visual Studio 2010
Coding Language
:
C#.NET
Database
:
SQL Server 2008
CONCLUSIONS
False non-match rates of fingerprint matchers are very high in the case of
severely distorted fingerprints. This generates a security hole in automatic
fingerprint recognition systems which can be utilized by criminals and terrorists.
For this reason, it is necessary to develop a fingerprint distortion detection and
rectification algorithms to fill the hole. This paper described a novel distorted
fingerprint detection and rectification algorithm. For distortion detection, the
registered ridge orientation map and period map of a fingerprint are used as the
feature vector and a SVM classifier is trained to classify the input fingerprint as
distorted or normal. For distortion rectification (or equivalently distortion field
estimation), a nearest neighbor regression approach is used to predict the
distortion field from the input distorted fingerprint and then the inverse of the
distortion field is used to transform the distorted fingerprint into a normal one.
The experimental results on FVC2004 DB1, Tsinghua DF database, and NIST
SD27 database showed that the proposed algorithm can improve recognition rate
of distorted fingerprints evidently. The proposed algorithm based on the features
extracted from the orientation field and minutiae satisfies the three essential
requirements for alteration detection algorithm:
A major limitation of the current approach is efficiency. Both detection and
rectification steps can be significantly speeded up if a robust and accurate
fingerprint registration algorithm can be developed. Another limitation is that the
current approach does not support rolled fingerprints. It is difficult to collect many
rolled fingerprints with various distortion types and meanwhile obtain accurate
distortion fields for learning statistical distortion model. It is our ongoing work to
address the above limitations.